Papers with Code 아카이브
Learning with noisy labels
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 20
- 보존된 평가 기록
- 194
Learning with noisy labels means When we say "noisy labels," we mean that an adversary has intentionally messed up the labels, which would have come from a "clean" distribution otherwise. This setting can also be used to cast learning from only positive and unlabeled data.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
UNICON: Combating Label Noise Through Uniform Selection and Contrastive Learning
Scalable Penalized Regression for Noise Detection in Learning with Noisy Labels
Selective-Supervised Contrastive Learning with Noisy Labels
On Learning Contrastive Representations for Learning with Noisy Labels
Robust Training under Label Noise by Over-parameterization
PENCIL: Deep Learning with Noisy Labels
L2B: Learning to Bootstrap Robust Models for Combating Label Noise
Identifiability of Label Noise Transition Matrix
Learning with Neighbor Consistency for Noisy Labels
Do We Need to Penalize Variance of Losses for Learning with Label Noise?
PARS: Pseudo-Label Aware Robust Sample Selection for Learning with Noisy Labels
Learning with Label Noise for Image Retrieval by Selecting Interactions
Hard Sample Aware Noise Robust Learning for Histopathology Image Classification
Sample Prior Guided Robust Model Learning to Suppress Noisy Labels
Learning with Noisy Labels by Efficient Transition Matrix Estimation to Combat Label Miscorrection
CoDiM: Learning with Noisy Labels via Contrastive Semi-Supervised Learning
SSR: An Efficient and Robust Framework for Learning with Unknown Label Noise
Learning to Rectify for Robust Learning with Noisy Labels
Adaptive Hierarchical Similarity Metric Learning with Noisy Labels
Prototypical Classifier for Robust Class-Imbalanced Learning
PropMix: Hard Sample Filtering and Proportional MixUp for Learning with Noisy Labels
Learning with Noisy Labels Revisited: A Study Using Real-World Human Annotations
Mitigating Memorization of Noisy Labels via Regularization between Representations
Clean or Annotate: How to Spend a Limited Data Collection Budget
Robust Temporal Ensembling for Learning with Noisy Labels
Learning to Aggregate and Refine Noisy Labels for Visual Sentiment Analysis
Co-Correcting: Noise-tolerant Medical Image Classification via mutual Label Correction
Confidence Adaptive Regularization for Deep Learning with Noisy Labels
Cooperative Learning for Noisy Supervision
Co-learning: Learning from Noisy Labels with Self-supervision
Learning with Noisy Labels via Sparse Regularization
Learning with Noisy Labels for Robust Point Cloud Segmentation
An Instance-Dependent Simulation Framework for Learning with Label Noise
Can Less be More? When Increasing-to-Balancing Label Noise Rates Considered Beneficial
Mitigating Memorization in Sample Selection for Learning with Noisy Labels
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.